Huosheng Xie

Bio: Huosheng Xie is an academic researcher from Fuzhou University. The author has contributed to research in topics: Face (geometry) & Facial recognition system. The author has an hindex of 1, co-authored 1 publications receiving 3 citations.

Face Gender Recognition based on Face Recognition Feature Vectors

Abstract: Automatic facial gender recognition is a widely used task in the field of computer vision, which is very easy for a human, but very challenging for computers. In this paper, a face gender classification algorithm based on face recognition feature vectors is proposed. Firstly, face detection and preprocessing are performed on the input images, and the faces are adjusted to a unified format. Secondly, the face recognition model is used to extract feature vectors as the representation of the face in the feature space. Finally, machine learning methods are used to classify the extracted feature vector. Meanwhile, this study uses t-distributed Stochastic Neighbor Embedding (T-SNE) to visualize the face recognition feature vectors to verify the effectiveness of the face recognition feature vectors on the issue of gender classification. The proposed method has achieved a recognition rate of 99.2% and 98.7% on the FEI dataset and the SCIEN dataset, respectively. Besides, it also achieves a recognition rate of 97.4% on the Asian star face dataset, outperforming existing methods, which shows that the proposed method is helpful for the research of facial gender.

DMCNet: Diversified Model Combination Network for Understanding Engagement from Video Screengrabs

Abstract: Engagement is an essential indicator of the Quality-of-Learning Experience (QoLE) and plays a major role in developing intelligent educational interfaces. The number of people learning through Massively Open Online Courses (MOOCs) and other online resources has been increasing rapidly because they provide us with the flexibility to learn from anywhere at any time. This provides a good learning experience for the students. However, such learning interface requires the ability to recognize the level of engagement of the students for a holistic learning experience. This is useful for both students and educators alike. However, understanding engagement is a challenging task, because of its subjectivity and ability to collect data. In this paper, we propose a variety of models that have been trained on an open-source dataset of video screengrabs. Our non-deep learning models are based on the combination of popular algorithms such as Histogram of Oriented Gradient (HOG), Support Vector Machine (SVM), Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF). The deep learning methods include Densely Connected Convolutional Networks (DenseNet-121), Residual Network (ResNet-18) and MobileNetV1. We show the performance of each models using a variety of metrics such as the Gini Index, Adjusted F-Measure (AGF), and Area Under receiver operating characteristic Curve (AUC). We use various dimensionality reduction techniques such as Principal Component Analysis (PCA) and t-Distributed Stochastic Neighbor Embedding (t-SNE) to understand the distribution of data in the feature sub-space. Our work will thereby assist the educators and students in obtaining a fruitful and efficient online learning experience.

Comparison of Machine Learning Algorithms Used for Skin Cancer Diagnosis

Abstract: The paper presents a comparison of automatic skin cancer diagnosis algorithms based on analyses of skin lesions photos. Two approaches are presented: the first one is based on the extraction of features from images using simple feature descriptors, and then the use of selected machine learning algorithms for the purpose of classification, and the second approach uses selected algorithms belonging to the subgroup of machine learning—deep learning, i.e., convolutional neural networks (CNN), which perform both the feature extraction and classification in one algorithm. The following algorithms were analyzed and compared: Logistic Regression, k-Nearest Neighbors, Naive Bayes, Decision Tree, Random Forest, and Support Vector Machine, and four CNN–VGG-16, ResNet60, InceptionV3, and Inception-ResNetV2 In the first variant, before the classification process, the image features were extracted using 4 different feature descriptors and combined in various combinations in order to obtain the most accurate image features vector, and thus the highest classification accuracy. The presented approaches have been validated using the image dataset from the ISIC database, which includes data from two categories—benign and malignant skin lesions. Common machine learning metrics and saved values of training time were used to evaluate the effectiveness and the performance (computational complexity) of the algorithms.

Real-time gender recognition based on eigen-features selection from facial images

Abstract: This paper proposed a novel image processing method combining Principal Component Analysis (PCA) and Genetic Algorithm (GA) to reduce the interference of facial expression, lighting or wear but extracting gender feature from frontal face. The collected facial images are first cropped and aligned automatically, then the gray-level information can be converted to feature vectors via PCA. After eigen-features are extracted with high classification performance by the aid of GA, the neural network classifier can be trained accordingly. Compared to the classification methods based on global gray-level information, the obtained classifier has better identification rate but half less used feature dimension, so the calculation load can substantially be reduced during training and identification procedures, which benefits to the development of a real-time identification system. Furthermore, FERET dataset and FEI dataset are used to validate the generality of the proposed method, where 92% and 94% accuracy rates of the gender recognition can be achieved respectively.

Gender Detection using Facial Features with Support Vector Machine

Abstract: Innovative security technologies have increased the need for accurate identification. Gender identification has been widespread use of image analysis in recent decades. The face is one of the most popular biometric features in image processing. In Image Processing and video surveillance, systems that automatically discern gender from facial photos are gaining prominence. This study discusses face traits and gender categorization. In this study, we created a technique with good runtime and efficiency to determine human gender using face photos. It uses characteristics taken from pre-processed face photographs of various ages. Support Vector Machine (SVM) Classification was used to determine class thresholds. Our method classifies UTK-FACE gender with 91.63% accuracy.

Face Recognition Using Convolution Neural Network Method with Discrete Cosine Transform Image for Login System

Abstract: These days, the application of image processing in computer vision is becoming more crucial. Some situations necessitate a solution based on computer vision and growing deep learning. One method continuously developed in deep learning is the Convolutional Neural Network, with MobileNet, EfficientNet, VGG16, and others being widely used architectures. Using the CNN architecture, the dataset consists primarily of images; the more datasets there are, the more image storage space will be required. Compression via the discrete cosine transform technique is a method to address this issue. We implement the DCT compression method in the present research to get around the system's limited storage space. Using DCT, we also compare compressed and uncompressed images. All users who had been trained with each test 5 times for a total of 150 tests were given the test. Based on testing findings, the size reduction rate for compressed and uncompressed images is measured at 25%. The case study presented is face recognition, and the training results indicate that the accuracy of compressed images using the DCT approach ranges from 91.33% to 100%. Still, the accuracy of uncompressed facial images ranges from 98.17% to 100%. In addition, the accuracy of the proposed CNN architecture has increased to 87.43%, while the accuracy of MobileNet has increased by 16.75%. The accuracy of EfficientNetB1 with noisy-student weights is measured at 74.91%, and the accuracy of EfficientNetB1 with imageNet weights can reach 100%. Facial biometric authentication using a deep learning algorithm and DCT-compressed images was successfully accomplished with an accuracy value of 95.33% and an error value of 4.67%.